Title :
Unsupervised classification based on decomposition of RISAT-1 images for oil spill detection
Author :
Kumar, Lingenahalli Jayadev Vijaya ; Kishore, J.K. ; Rao, P. Kesava
Author_Institution :
Master Control Facility, ISRO, Hassan, India
Abstract :
The main aim of this paper is to discuss the identification of oil spill using Hybrid polarity SAR architecture of India´s first Radar imaging Satellite RISAT-1 SAR images. The RISAT-1´s Hybrid polarity SAR architecture and imaging modes are discussed. The characterization of EM waves with polarization ellipse and polarization state are discussed. The Stokes parameters S1,S2,S3,S4 and its importance for deriving ellipticity and relative phase angle is described. The new m-chi and m-delta decomposition methods are used in India´s Chandrayaan-1 mission for water-ice identification are illustrated. These methods are applied to Norway oil spill image of RISAT-1 to identify the oil spill region and discriminate look alikes. The preliminary results are encouraging to highlight the potential of unsupervised classification for identification of oil spill with SAR images.
Keywords :
geophysical image processing; image classification; marine pollution; object recognition; oceanographic techniques; oil pollution; radar imaging; radar polarimetry; remote sensing; spaceborne radar; EM wave characterization; India Chandrayaan-1 mission; India first Radar imaging Satellite; Norway oil spill image; RISAT-1 SAR images; RISAT-1 hybrid polarity SAR architecture; RISAT-1 image decomposition; Stokes parameter; ellipticity; imaging modes; m-chi decomposition method; m-delta decomposition method; oil spill detection; oil spill identification; oil spill region identification; phase angle; polarization ellipse; polarization state; unsupervised classification; water-ice identification; Electromagnetic fields; Image resolution; Imaging; Polarization; Radar imaging; Stokes parameters; Synthetic aperture radar; Oil Spill; RISAT-1; SAR;
Conference_Titel :
Advances in Computing, Communications and Informatics (ICACCI), 2013 International Conference on
Conference_Location :
Mysore
Print_ISBN :
978-1-4799-2432-5
DOI :
10.1109/ICACCI.2013.6637266